Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The gentle sway of the hammock, the rustling of leaves in the gentle breeze, the warmth of the sun on his face – Leo was in his element. The afternoon was pure bliss, a moment of tranquil perfection that he wanted to savour. He picked up his phone, finally feeling ready to start work on his next piece. The he saw a notification. Someone had tattooed his charcoal sketch of a lighthouse onto their ankle.

A broad, genuine grin spread across his features. He felt an inner glow, a warmth that radiated from his core. He’d never felt so validated. He felt like he could fly, or leap. He immediately responded to the message.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

This story is one of 1,000 stories generated for the emotion happy. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 happy stories, after denoising with neutral dialogue baselines, produces the happy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the happy vector is projected through the unembedding matrix.

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
🀩0.495
Suppressed:
S-0.896
😞-0.430
ness-0.410
γγ‚Œγ§γ‚‚-0.387
L-0.379